sched/headers: Introduce kernel/sched/build_utility.c and build multiple .c files there

Collect all utility functionality source code files into a single kernel/sched/build_utility.c file,
via #include-ing the .c files:

    kernel/sched/clock.c
    kernel/sched/completion.c
    kernel/sched/loadavg.c
    kernel/sched/swait.c
    kernel/sched/wait_bit.c
    kernel/sched/wait.c

CONFIG_CPU_FREQ:
    kernel/sched/cpufreq.c

CONFIG_CPU_FREQ_GOV_SCHEDUTIL:
    kernel/sched/cpufreq_schedutil.c

CONFIG_CGROUP_CPUACCT:
    kernel/sched/cpuacct.c

CONFIG_SCHED_DEBUG:
    kernel/sched/debug.c

CONFIG_SCHEDSTATS:
    kernel/sched/stats.c

CONFIG_SMP:
   kernel/sched/cpupri.c
   kernel/sched/stop_task.c
   kernel/sched/topology.c

CONFIG_SCHED_CORE:
   kernel/sched/core_sched.c

CONFIG_PSI:
   kernel/sched/psi.c

CONFIG_MEMBARRIER:
   kernel/sched/membarrier.c

CONFIG_CPU_ISOLATION:
   kernel/sched/isolation.c

CONFIG_SCHED_AUTOGROUP:
   kernel/sched/autogroup.c

The goal is to amortize the 60+ KLOC header bloat from over a dozen build units into
a single build unit.

The build time of build_utility.c also roughly matches the build time of core.c and
fair.c - allowing better load-balancing of scheduler-only rebuilds.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>

kernel/sched/Makefile

@@ -22,18 +22,13 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
-obj-y += core.o loadavg.o clock.o cputime.o
-obj-y += idle.o fair.o rt.o deadline.o
-obj-y += wait.o wait_bit.o swait.o completion.o
-
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o
-obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
-obj-$(CONFIG_SCHEDSTATS) += stats.o
-obj-$(CONFIG_SCHED_DEBUG) += debug.o
-obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
-obj-$(CONFIG_CPU_FREQ) += cpufreq.o
-obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
-obj-$(CONFIG_MEMBARRIER) += membarrier.o
-obj-$(CONFIG_CPU_ISOLATION) += isolation.o
-obj-$(CONFIG_PSI) += psi.o
-obj-$(CONFIG_SCHED_CORE) += core_sched.o
+#
+# Build efficiency:
+#
+# These compilation units have roughly the same size and complexity - so their
+# build parallelizes well and finishes roughly at once:
+#
+obj-y += core.o
+obj-y += fair.o
+obj-y += build_utility.o
+obj-y += idle.o rt.o deadline.o cputime.o cpudeadline.o pelt.o

kernel/sched/autogroup.c

 // SPDX-License-Identifier: GPL-2.0
+
 /*
  * Auto-group scheduling implementation:
  */
-#include <linux/nospec.h>
-#include "sched.h"
 
 unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
 static struct autogroup autogroup_default;

kernel/sched/build_utility.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * These are various utility functions of the scheduler,
+ * built in a single compilation unit for build efficiency reasons.
+ *
+ * ( Incidentally, the size of the compilation unit is roughly
+ *   comparable to core.c, fair.c, smp.c and policy.c, the other
+ *   big compilation units. This helps balance build time, while
+ *   coalescing source files to amortize header inclusion
+ *   cost. )
+ */
+
+#include "sched.h"
+#include "sched-pelt.h"
+
+#include <linux/sched_clock.h>
+
+#include "clock.c"
+
+#ifdef CONFIG_CGROUP_CPUACCT
+# include "cpuacct.c"
+#endif
+
+#ifdef CONFIG_CPU_FREQ
+# include "cpufreq.c"
+#endif
+
+#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
+# include "cpufreq_schedutil.c"
+#endif
+
+#ifdef CONFIG_SCHED_DEBUG
+# include "debug.c"
+#endif
+
+#ifdef CONFIG_SCHEDSTATS
+# include "stats.c"
+#endif
+
+#include "loadavg.c"
+#include "completion.c"
+#include "swait.c"
+#include "wait_bit.c"
+#include "wait.c"
+
+#ifdef CONFIG_SMP
+# include "cpupri.c"
+# include "stop_task.c"
+# include "topology.c"
+#endif
+
+#ifdef CONFIG_SCHED_CORE
+# include "core_sched.c"
+#endif
+
+#ifdef CONFIG_PSI
+# include "psi.c"
+#endif
+
+#ifdef CONFIG_MEMBARRIER
+# include "membarrier.c"
+#endif
+
+#ifdef CONFIG_CPU_ISOLATION
+# include "isolation.c"
+#endif
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+# include "autogroup.c"
+#endif

kernel/sched/clock.c

@@ -53,8 +53,6 @@
  * that is otherwise invisible (TSC gets stopped).
  *
  */
-#include "sched.h"
-#include <linux/sched_clock.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.

kernel/sched/completion.c

 // SPDX-License-Identifier: GPL-2.0
+
 /*
  * Generic wait-for-completion handler;
  *
@@ -11,7 +12,6 @@
  * typically be used for exclusion which gives rise to priority inversion.
  * Waiting for completion is a typically sync point, but not an exclusion point.
  */
-#include "sched.h"
 
 /**
  * complete: - signals a single thread waiting on this completion

kernel/sched/core_sched.c

 // SPDX-License-Identifier: GPL-2.0-only
 
-#include <linux/prctl.h>
-#include "sched.h"
-
 /*
  * A simple wrapper around refcount. An allocated sched_core_cookie's
  * address is used to compute the cookie of the task.

kernel/sched/cpuacct.c

 // SPDX-License-Identifier: GPL-2.0
+
 /*
  * CPU accounting code for task groups.
  *
  * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
  * (balbir@in.ibm.com).
  */
-#include <asm/irq_regs.h>
-#include "sched.h"
 
 /* Time spent by the tasks of the CPU accounting group executing in ... */
 enum cpuacct_stat_index {

kernel/sched/cpufreq.c

@@ -5,9 +5,6 @@
  * Copyright (C) 2016, Intel Corporation
  * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  */
-#include <linux/cpufreq.h>
-
-#include "sched.h"
 
 DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
 

kernel/sched/cpufreq_schedutil.c

@@ -6,13 +6,6 @@
  * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include "sched.h"
-
-#include <linux/sched/cpufreq.h>
-#include <trace/events/power.h>
-
 #define IOWAIT_BOOST_MIN	(SCHED_CAPACITY_SCALE / 8)
 
 struct sugov_tunables {

kernel/sched/cpupri.c

@@ -22,7 +22,6 @@
  *  worst case complexity of O(min(101, nr_domcpus)), though the scenario that
  *  yields the worst case search is fairly contrived.
  */
-#include "sched.h"
 
 /*
  * p->rt_priority   p->prio   newpri   cpupri

kernel/sched/debug.c

@@ -6,7 +6,6 @@
  *
  * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar
  */
-#include "sched.h"
 
 /*
  * This allows printing both to /proc/sched_debug and

kernel/sched/isolation.c

@@ -7,7 +7,6 @@
  * Copyright (C) 2017-2018 SUSE, Frederic Weisbecker
  *
  */
-#include "sched.h"
 
 enum hk_flags {
 	HK_FLAG_TIMER		= BIT(HK_TYPE_TIMER),

kernel/sched/loadavg.c

@@ -6,7 +6,6 @@
  * figure. Its a silly number but people think its important. We go through
  * great pains to make it work on big machines and tickless kernels.
  */
-#include "sched.h"
 
 /*
  * Global load-average calculations

kernel/sched/membarrier.c

@@ -4,7 +4,6 @@
  *
  * membarrier system call
  */
-#include "sched.h"
 
 /*
  * For documentation purposes, here are some membarrier ordering

kernel/sched/psi.c

@@ -137,21 +137,6 @@
  * sampling of the aggregate task states would be.
  */
 
-#include "../workqueue_internal.h"
-#include <linux/sched/loadavg.h>
-#include <linux/seq_file.h>
-#include <linux/proc_fs.h>
-#include <linux/seqlock.h>
-#include <linux/uaccess.h>
-#include <linux/cgroup.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/ctype.h>
-#include <linux/file.h>
-#include <linux/poll.h>
-#include <linux/psi.h>
-#include "sched.h"
-
 static int psi_bug __read_mostly;
 
 DEFINE_STATIC_KEY_FALSE(psi_disabled);

kernel/sched/sched.h

@@ -6,7 +6,25 @@
 #define _KERNEL_SCHED_SCHED_H
 
 #include <linux/sched.h>
+#include <linux/cpumask.h>
+#include <linux/ktime_api.h>
+#include <linux/cgroup_api.h>
+#include <linux/topology.h>
+#include <linux/prctl.h>
+#include <linux/ptrace_api.h>
+#include <linux/gfp_api.h>
+#include <linux/sched/clock.h>
+#include <linux/workqueue_api.h>
+#include <linux/tick.h>
+#include <linux/ktime_api.h>
+#include <linux/swait_api.h>
+#include <linux/hashtable_api.h>
+#include <linux/cpufreq.h>
+#include <linux/utsname.h>
 
+#include <asm/irq_regs.h>
+
+#include <linux/sched/affinity.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/coredump.h>
@@ -24,6 +42,7 @@
 #include <linux/sched/nohz.h>
 #include <linux/sched/numa_balancing.h>
 #include <linux/sched/prio.h>
+#include <linux/sched/rseq_api.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/smt.h>
@@ -31,6 +50,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
+#include <linux/sched/thread_info_api.h>
 #include <linux/sched/topology.h>
 #include <linux/sched/user.h>
 #include <linux/sched/wake_q.h>
@@ -69,8 +89,7 @@
 #include <linux/syscalls.h>
 #include <linux/task_work.h>
 #include <linux/tsacct_kern.h>
-
-#include <asm/tlb.h>
+#include <linux/hrtimer_api.h>
 
 #ifdef CONFIG_PARAVIRT
 # include <asm/paravirt.h>
@@ -87,6 +106,40 @@
 # define SCHED_WARN_ON(x)	({ (void)(x), 0; })
 #endif
 
+#include <linux/bitmap.h>
+#include <linux/capability.h>
+#include <linux/cgroup.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask_api.h>
+#include <linux/ctype.h>
+#include <linux/file.h>
+#include <linux/jiffies.h>
+#include <linux/kref_api.h>
+#include <linux/lockdep_api.h>
+#include <linux/module.h>
+#include <linux/mutex_api.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/psi.h>
+#include <linux/sched/affinity.h>
+#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/rseq_api.h>
+#include <linux/seq_file.h>
+#include <linux/seqlock.h>
+#include <linux/syscalls_api.h>
+#include <linux/syscalls.h>
+#include <linux/topology.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/wait_api.h>
+#include <linux/workqueue_api.h>
+
+#include <trace/events/power.h>
+
+#include "../workqueue_internal.h"
+
 struct rq;
 struct cpuidle_state;
 

kernel/sched/stats.c

@@ -2,7 +2,6 @@
 /*
  * /proc/schedstat implementation
  */
-#include "sched.h"
 
 void __update_stats_wait_start(struct rq *rq, struct task_struct *p,
 			       struct sched_statistics *stats)

kernel/sched/stop_task.c

@@ -7,7 +7,6 @@
  *
  * See kernel/stop_machine.c
  */
-#include "sched.h"
 
 #ifdef CONFIG_SMP
 static int

kernel/sched/swait.c

@@ -2,7 +2,6 @@
 /*
  * <linux/swait.h> (simple wait queues ) implementation:
  */
-#include "sched.h"
 
 void __init_swait_queue_head(struct swait_queue_head *q, const char *name,
 			     struct lock_class_key *key)

kernel/sched/topology.c

@@ -2,7 +2,6 @@
 /*
  * Scheduler topology setup/handling methods
  */
-#include "sched.h"
 
 DEFINE_MUTEX(sched_domains_mutex);
 

kernel/sched/wait.c

@@ -4,7 +4,6 @@
  *
  * (C) 2004 Nadia Yvette Chambers, Oracle
  */
-#include "sched.h"
 
 void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key)
 {

kernel/sched/wait_bit.c

 // SPDX-License-Identifier: GPL-2.0-only
+
 /*
  * The implementation of the wait_bit*() and related waiting APIs:
  */
-#include "sched.h"
 
 #define WAIT_TABLE_BITS 8
 #define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS)